Lines Matching refs:userspace

12 sg_table and exposed to userspace as a file descriptor to allow passing
55 Mostly a DMA buffer file descriptor is simply an opaque object for userspace,
80   To avoid this problem, userspace must have a way to request O_CLOEXEC
83   userspace control setting of O_CLOEXEC flag passed in to dma_buf_fd().
229   The time this fence completes is entirely under userspace's control.
235   that userspace uses for synchronization across engines or with the CPU, which
243 Common to all these schemes is that userspace controls the dependencies of these
246 protect against malicious userspace:
248 * Only the kernel knows about all DMA fence dependencies, userspace is not aware
251 * Only userspace knows about all dependencies in indefinite fences and when
254 Furthermore the kernel has to be able to hold up userspace command submission
267       userspace [label="userspace controlled fences"]
268       kernel -> userspace [label="memory management"]
269       userspace -> kernel [label="Future fence, fence proxy, ..."]
271       { rank=same; kernel userspace }
275 through memory management dependencies which userspace is unaware of, which
277 userspace's perspective, do not contain a deadlock.  In such a mixed fencing
284 * No future fences, proxy fences or userspace fences imported as DMA fences,
288   userspace is allowed to use userspace fencing or long running compute
302 synchronization. Synchronization fences controlled by userspace must be used
306 Linux rely on DMA fences, which means without an entirely new userspace stack
307 built on top of userspace fences, they cannot benefit from recoverable page
364 problem is new, because some other CPU thread in userspace might
365 hit a page fault which holds up a userspace fence - supporting page faults on